Document genre (e.g. scientific article, fiction, advertisement) is closely bound to the physical and conceptual structure of the document as well as the level of depth and reliability of the information found within the text. Hence, it is useful as a reference for comparing documents on the basis of metrics other than topical similarity. Despite its usefulness, the success of previous attempts to automate genre classification is somewhat unsatisfactory. In this talk, we will revisit the value of genre within context-driven information seeking activities, and re-introduce some methods that have already been studied, to suggest some avenues of taking the research forward.
Return to seminars